Solved
Regular Learner
Posts: 1

# Proc Mixed

I was running a Proc Mixed model a test using code from the SAS website. I found that the solution option for the random statement produced the random effects coefficients (intercept and slope) but also produced a standard error of the prediction that was then used to calculate a t statistic for both coefficients.  I have never seen this anywhere else and it seems that calculating the t stat might be useful.  Can anyone say exactly how the standard error of the predictions was calculated? The manual is very vague.

Accepted Solutions
Solution
‎09-02-2016 01:32 AM
Valued Guide
Posts: 684

## Re: Proc Mixed

Since you are interested in Mixed Models, you need to get the book "SAS for Mixed Models, 2nd edition" by Littelll et al. (2006). Lots on random effects.  There will be a third edition coming out in 2017 or 2018.

All Replies
Valued Guide
Posts: 684

## Re: Proc Mixed

This is actually standard practice. Except for some very simple situations, there is no straight-forward scalar equation for the standard error for the predicted random effect coefficient (really should be called square root of the variance of the prediciton). You typically can only write this using matrix notation. In the User's Guide, this is described under Estimating Fixed and Random Effects in the Mixed Model in the Theory Section (see the C^ matrix). The relevant section is for gamma^ - gamma vector.

http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_mixed_detail...

Solution
‎09-02-2016 01:32 AM
Valued Guide
Posts: 684

## Re: Proc Mixed

Since you are interested in Mixed Models, you need to get the book "SAS for Mixed Models, 2nd edition" by Littelll et al. (2006). Lots on random effects.  There will be a third edition coming out in 2017 or 2018.

New Contributor
Posts: 2

## Re: Proc Mixed

Dear : Mr/Mrs. lvm

According to your comment on. I concern that you are the best instructor to teach me about SAS.

My name is Rayudika who is doctoral student of SUT in Thailand. Indeed, recently time of this month is conducting of my synthesis from data meta analysis. To be honest, I never use SAS program, consequently, I know nothing about that. My pleasure to accept your considerable is coming true when you give me it.
My data : Factor (A) effect for parameter (X) with using separately
methods : Method 1 and method 2.
Would you like to suggest me to input the data (SAS language code) on PROC MIX ?

Yours sincerely,
Rayudika Aprilia Patindra Purba
Animal Production, SUT, Thailand
rayudikaapp.007@gmail.com
14 December 2016
☑ This topic is solved.